Comparative analysis of machine learning approaches on the prediction of the electronic properties of perovskites: A case study of ABX3 and A2BB’X6

Chenebuah, Ericsson Tetteh; Nganbe, Michel; Tchagang, Alain B.

doi:10.1016/j.mtcomm.2021.102462

Cited by 23 publications

(35 citation statements)

References 81 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The sharing of available data is becoming increasingly important in order to continue to make progress in the design and discovery of new perovskite-type phases [70][71][72]. In the future, structureproperty relationships and their qualified evaluation will continue to play a large and important role [73,74], which is why we have also followed this approach.…”

Section: Discussionmentioning

confidence: 99%

The Development of New Perovskite-Type Oxygen Transport Membranes Using Machine Learning

et al. 2022

View full text Add to dashboard Cite

The aim of this work is to predict suitable chemical compositions for the development of new ceramic oxygen gas separation membranes, avoiding doping with toxic cobalt or expensive rare earths. For this purpose, we have chosen the system Sr1−xBax(Ti1−y−zVyFez)O3−δ (cubic perovskite-type phases). We have evaluated available experimental data, determined missing crystallographic information using bond-valence modeling and programmed a Python code to be able to generate training data sets for property predictions using machine learning. Indeed, suitable compositions of cubic perovskite-type phases can be predicted in this way, allowing for larger electronic conductivities of up to σe = 1.6 S/cm and oxygen conductivities of up to σi = 0.008 S/cm at T = 1173 K and an oxygen partial pressure pO2 = 10−15 bar, thus enabling practical applications.

show abstract

Section: Discussionmentioning

confidence: 99%

The Development of New Perovskite-Type Oxygen Transport Membranes Using Machine Learning

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Previously (Balachandran et al, 2018;Bartel et al, 2019;Chenebuah et al, 2021). We present the contribution of those variables to oxyhydrides stabilities by ranking their feature importance in classifying the oxyhydrides with ΔE hull = 100 meV/atom as a threshold (Figure 5, Figure S2).…”

Section: Oxyhydrides Categorymentioning

confidence: 99%

“…The permutation-based importance of 25 features (Table S1 in supplementary material) consisting of 20 elemental properties and five structural/compositional descriptors were evaluated by the random forest algorithm (Breiman, 2001) upon classifying oxyhydrides stabilities. Those empirically considered descriptors are commonly used in other studies to predict unmixed compounds' stabilities and to analyze stability relationship (Balachandran et al, 2018;Bartel et al, 2019;Chenebuah et al, 2021). The tolerance factor t bv (Matsui et al, 2020) that measures the degree of geometric mismatch in the layered-perovskite (K 2 NiF 4 -type) structure is defined as:…”

Section: Features Generationmentioning

confidence: 99%

“…In order to use the ML model trained by the unmixed compounds to screen the mixed compounds, the feature dimension of the mixed compounds was kept as the unmixed ones. The A-site elemental properties (f A ) were estimated by the arithmetic mean of the two mixed ions (i.e., f A = (f A1 + f A2 )/2) following previous studies (Bartel et al, 2019;Chenebuah et al, 2021;Liu et al, 2022).…”

Section: Features Generationmentioning

confidence: 99%

“…The highest conductivity of a series of the oxyhydrides can be achieved in the A-mixed compounds LaSrLiH 2 O 2 with 0.21 mS/cm at 590 K (Kobayashi et al, 2016). However, the survey of the mixed materials is challenged by an enormous quantity of their configurations, and therefore calls for more robust search methods such as machine learning (ML) algorithm (Ye et al, 2018;Chenebuah et al, 2021;Talapatra et al, 2021;Tao et al, 2021). While using the ML model to survey materials with promising properties can be extremely powerful, a key roadblock in our task and many similar studies (Cubuk et al, 2019;Jha et al, 2019;Hashimoto et al, 2020;Chen and Ong, 2021;Hanaoka, 2022) to utilize ML approach often points to the unavailability of the database due to their huge quantity.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Computation-accelerated discovery of the K2NiF4-type oxyhydrides combing density functional theory and machine learning approach

et al. 2022

View full text Add to dashboard Cite

The emerging K2NiF4-type oxyhydrides with unique hydride ions (H−) and O2- coexisting in the anion sublattice offer superior functionalities for numerous applications. However, the exploration and innovations of the oxyhydrides are challenged by their rarity as a limited number of compounds reported in experiments, owing to the stringent laboratory conditions. Herein, we employed a suite of computations involving ab initio methods, informatics and machine learning to investigate the stability relationship of the K2NiF4-type oxyhydrides. The comprehensive stability map of the oxyhydrides chemical space was constructed to identify 76 new compounds with good thermodynamic stabilities using the high-throughput computations. Based on the established database, we reveal geometric constraints and electronegativities of cationic elements as significant factors governing the oxyhydrides stabilities via informatics tools. Besides fixed stoichiometry compounds, mixed-cation oxyhydrides can provide promising properties due to the enhancement of compositional tunability. However, the exploration of the mixed compounds is hindered by their huge quantity and the rarity of stable oxyhydrides. Therefore, we propose a two-step machine learning workflow consisting of a simple transfer learning to discover 114 formable oxyhydrides from thousands of unknown mixed compositions. The predicted high H− conductivities of the representative oxyhydrides indicate their suitability as energy conversion materials. Our study provides an insight into the oxyhydrides chemistry which is applicable to other mixed-anion systems, and demonstrates an efficient computational paradigm for other materials design applications, which are challenged by the unavailable and highly unbalanced materials database.

show abstract

Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects

Liu

Tan

Liang

et al. 2023

Adv Funct Materials

View full text Add to dashboard Cite

Data-driven epoch, the development of machine learning (ML) in materials and device design is an irreversible trend. Its ability and efficiency to handle nonlinear and game-playing problems is unmatched by traditional simulation computing software and trial-error experiments. Perovskite solar cells are complex physicochemical devices (systems) that consist of perovskite materials, transport layer materials, and electrodes. Predicting the physicochemical properties and screening the component materials related to perovskite solar cells is the strong point of ML. However, the applications of ML in perovskite solar cells and component materials has only begun to boom in the last two years, so it is necessary to provide a review of the involved ML technologies, the application status, the facing urgent challenges and the development blueprint.

show abstract

Comparative analysis of machine learning approaches on the prediction of the electronic properties of perovskites: A case study of ABX3 and A2BB’X6

Cited by 23 publications

References 81 publications

The Development of New Perovskite-Type Oxygen Transport Membranes Using Machine Learning

The Development of New Perovskite-Type Oxygen Transport Membranes Using Machine Learning

Computation-accelerated discovery of the K2NiF4-type oxyhydrides combing density functional theory and machine learning approach

Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects

Contact Info

Product

Resources

About